INDEX

Explanations

programming-related terms and syntax elements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

mathematical formatting for math symbols

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.37

intenant

-0.36

 peup

-0.35

 صوتيه

-0.35

ushchev

-0.34

sembly

-0.33

Goed

-0.33

primaryColor

-0.33

dismiss

-0.32

codehaus

-0.32

POSITIVE LOGITS

 awakeFromNib

1.06

IActionResult

0.96

>{@

0.94

AssignableFrom

0.94

InSection

0.86

astify

0.84

awakeFromNib

0.82

multirow

0.77

 שוליים

0.77

ResponseWriter

0.76

Activations Density 0.013%

programming-related terms and syntax elements

mathematical formatting for math symbols

No Comments

No Known Activations